Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4866 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3237. Min Range: -5.3237

Max Act: 5.3237. Min Act: -0.0000

Data Index: 1406519 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 5.3237. Min Range: -5.3237

Max Act: 4.9419. Min Act: -0.0000

Data Index: 1473107 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 5.3237. Min Range: -5.3237

Max Act: 4.0726. Min Act: -0.0000

Data Index: 1514935 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.9984. Min Act: -0.0000

Data Index: 1632165 (Python Code)

Max Activating Token Index: 207

Text #4

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.6542. Min Act: -0.0000

Data Index: 1376192 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.6336. Min Act: -0.0000

Data Index: 1419939 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.5823. Min Act: -0.0000

Data Index: 1649829 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.4650. Min Act: -0.0000

Data Index: 1490128 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.5708. Min Act: -0.0000

Data Index: 1442299 (Python Code)

Max Activating Token Index: 625

Text #9

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.4090. Min Act: -0.0000

Data Index: 1498290 (Python Code)

Max Activating Token Index: 436

Text #10

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.3786. Min Act: -0.0000

Data Index: 1530380 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.3592. Min Act: -0.0000

Data Index: 1564580 (Python Code)

Max Activating Token Index: 238

Text #12

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.2966. Min Act: -0.0000

Data Index: 1556002 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.2564. Min Act: -0.0000

Data Index: 1415071 (Python Code)

Max Activating Token Index: 677

Text #14

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.3431. Min Act: -0.0000

Data Index: 1653236 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.1716. Min Act: -0.0000

Data Index: 1397129 (Python Code)

Max Activating Token Index: 190

Text #16

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.1663. Min Act: -0.0000

Data Index: 1476190 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.2414. Min Act: -0.0000

Data Index: 1535269 (Python Code)

Max Activating Token Index: 1000

Text #18

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.0960. Min Act: -0.0000

Data Index: 74880 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 5.3237. Min Range: -5.3237

Max Act: 3.0772. Min Act: -0.0000

Data Index: 1609973 (Python Code)

Max Activating Token Index: 897